Added support for Google Custom Search API

This pull request adds functionality to the project to allow for a choice between the original Google search method and the Google Custom Search API. The google_search method uses the original method of scraping the HTML from the search results page, using googlesearch-python, while the google_official_search method uses the Google Custom Search API to retrieve search results.

How to test:

To test the functionality, ensure that you have valid API keys and search engine IDs for both the Google search method and the Google Custom Search API. You can set these values in your environment variables as described in the README.md file.

Additional Notes:

This pull request only adds functionality and makes improvements to existing code. No new features or major changes have been introduced.

scripts/commands.py

@@ -10,6 +10,9 @@ from file_operations import read_file, write_to_file, append_to_file, delete_fil
 from execute_code import execute_python_file
 from json_parser import fix_and_parse_json
 from googlesearch import search
+from googleapiclient.discovery import build
+from googleapiclient.errors import HttpError
+
 cfg = Config()
 
 
@@ -44,7 +47,13 @@ def get_command(response):
 def execute_command(command_name, arguments):
     try:
         if command_name == "google":
-            return google_search(arguments["input"])
+            print("Using Google search method")
+            # Check if the Google API key is set and use the official search method
+            # If the API key is not set or has only whitespaces, use the unofficial search method
+            if cfg.google_api_key and (cfg.google_api_key.strip() if cfg.google_api_key else None):
+                return google_official_search(arguments["input"])
+            else:
+                return google_search(arguments["input"])
         elif command_name == "memory_add":
             return commit_memory(arguments["string"])
         elif command_name == "memory_del":
@@ -108,6 +117,40 @@ def google_search(query, num_results=8):
 
     return json.dumps(search_results, ensure_ascii=False, indent=4)
 
+def google_official_search(query, num_results=8):
+    from googleapiclient.discovery import build
+    from googleapiclient.errors import HttpError
+    import json
+
+    try:
+        # Get the Google API key and Custom Search Engine ID from the config file
+        api_key = cfg.google_api_key
+        custom_search_engine_id = cfg.custom_search_engine_id
+
+        # Initialize the Custom Search API service
+        service = build("customsearch", "v1", developerKey=api_key)
+        
+        # Send the search query and retrieve the results
+        result = service.cse().list(q=query, cx=custom_search_engine_id, num=num_results).execute()
+
+        # Extract the search result items from the response
+        search_results = result.get("items", [])
+        
+        # Create a list of only the URLs from the search results
+        search_results_links = [item["link"] for item in search_results]
+
+    except HttpError as e:
+        # Handle errors in the API call
+        error_details = json.loads(e.content.decode())
+        
+        # Check if the error is related to an invalid or missing API key
+        if error_details.get("error", {}).get("code") == 403 and "invalid API key" in error_details.get("error", {}).get("message", ""):
+            return "Error: The provided Google API key is invalid or missing."
+        else:
+            return f"Error: {e}"
+
+    # Return the list of search result URLs
+    return search_results_links
 
 def browse_website(url):
     summary = get_text_summary(url)